The identification of patients with aggressive cancer who require immediate therapy is a health challenge in low-income and middle-income countries. Limited pathology resources, high healthcare costs and large-case loads call for the development of advanced standalone diagnostics. Here, we report and validate an automated, low-cost point-of-care device for the molecular diagnosis of aggressive lymphomas. The device uses contrast-enhanced microholography and a deep-learning algorithm to directly analyse percutaneously obtained fine-needle aspirates. We show the feasibility and high accuracy of the device in cells, as well as the prospective validation of the results in 40 patients clinically referred for image-guided aspiration of nodal mass lesions suspicious for lymphoma. Automated analysis of human samples with the portable device should allow for the accurate classification of patients with benign and malignant adenopathy.

The global burden of cancer, severe diagnostic bottlenecks in underserved regions, and underfunded health care systems are fueling the need for inexpensive, rapid, and treatment-informative diagnostics. On the basis of advances in computational optics and deep learning, we have developed a low-cost digital system, termed AIDA (artificial intelligence diffraction analysis), for breast cancer diagnosis of fine needle aspirates. Here, we show high accuracy (>90%) in (i) recognizing cells directly from diffraction patterns and (ii) classifying breast cancer types using deep-learning-based analysis of sample aspirates. The image algorithm is fast, enabling cellular analyses at high throughput (∼3 s per 1000 cells), and the unsupervised processing allows use by lower skill health care workers. AIDA can perform quantitative molecular profiling on individual cells, revealing intratumor molecular heterogeneity, and has the potential to improve cancer diagnosis and treatment. The system could be further developed for other cancers and thus find widespread use in global health.